Screening device, method, and system for structural heart disease

Abstract

A wireless wearable sensor device, system, method, and non-transitory computer readable medium for screening for structural heart disease based on electrocardiogram, phonocardiogram, and/or accelerometer signals on a patient's skin surface.

We claim: 
     
       1. A method of screening of structural heart disease using a wearable sensor device measuring one or more leads of electrocardiogram, phonocardiogram, and accelerometer signals at chest skin surface, the method comprising:
 measuring, by at least one sensor, electrocardiogram (ECG), phonocardiogram (PCG), and accelerometer (ACC) signals on a patient's skin surface and sending the ECG, PCG, and ACC signals to a processor; 
 executing, by the processor, an application stored in a memory to:
 filter the ECG, PCG, and ACC signals to remove noise; 
 align the filtered ECG, PCG, and ACC signals in time, taking into account any propagation delay; 
 divide the measured signals into one or more sequences based on a measure of body acceleration, 
 wherein the dividing the measured signals into one or more sequences based on a measure of body acceleration includes the time aligned ECG, PCG, and ACC signals are divided into respective windows of arbitrary durations to obtain the one or more sequences; 
 screen decisions on the one or more sequences of the ECG and PCG derived features; 
 determine sequences of aggregate screening decisions; and 
 combine the aggregate screening decisions to screen for structural heart disease and output an indication of a presence of the screened structural heart disease to a display. 
 
 
     
     
       2. The method of  claim 1 , wherein the measure of body acceleration is derived from the accelerometer signals. 
     
     
       3. The method of  claim 1 , wherein the screening decisions includes applying a screening algorithm on the one or more sequences of the electrocardiogram and phonocardiogram derived features. 
     
     
       4. The method of  claim 1 , wherein the screening decisions on one or more sequences of electrocardiogram and phonocardiogram derived features includes feeding each sequence individually into a sequence screening engine, wherein the sequence screening engine relies on two categories of features, including criteria for sequencing data. 
     
     
       5. The method of  claim 4 , wherein the criteria for sequencing data segmentation specific features are derived after segmenting the PCG signals into constituent heart phases including S1, systole, S2, and diastole for each heartbeat. 
     
     
       6. The method of  claim 4 , wherein the screening decisions on one or more sequences of electrocardiogram and phonocardiogram derived features further includes employing independently single channels of segmentation including physiological segmentation and model based segmentation to determine constituent heart stages. 
     
     
       7. The method of  claim 6 , wherein a weighted sum of single channel are used to obtain a final position of the segmentation. 
     
     
       8. The method of  claim 1 , further comprising directly deriving sequence specific features from the second sequence without any segmentation. 
     
     
       9. The method of  claim 1 , wherein the combining individual decisions to screen for the structural heart disease includes aggregating the screening and fed into a sequence aggregate model to determine a final decision for the structural heart disease. 
     
     
       10. A method of screening of structural heart disease using a wearable sensor device measuring one or more leads of electrocardiogram, phonocardiogram, and accelerometer signals at chest skin surface, the method comprising:
 measuring, by at least one sensor, electrocardiogram (ECG), phonocardiogram (PCG), and accelerometer (ACC) signals on a patient's skin surface and sending the ECG, PCG, and ACC signals to a processor; 
 executing, by the processor, an application stored in a memory to: 
 divide the measured signals into one or more sequences based on a measure of body acceleration; 
 screen decisions on the one or more sequences of the ECG and PCG derived features; 
 determine sequences of aggregate screening decisions; 
 combine the aggregate screening decisions to screen for structural heart disease; and 
 output an indication of a presence of the screened structural heart disease to a display; 
 wherein the screening decisions on one or more sequences of electrocardiogram and phonocardiogram derived features includes feeding each sequence individually into a sequence screening engine, wherein the sequence screening engine relies on two categories of features, including segmentation specific features and sequence specific features to screen the sequence; 
 wherein the screening decisions on one or more sequences of electrocardiogram and phonocardiogram derived features further includes employing independently single channels of segmentation including physiological segmentation and model based segmentation to determine constituent heart stages; and 
 wherein the physiological segmentation includes: 
 determining fiducial points in a first sequence including a peak of an R wave, and an end of a T wave for each heartbeat; 
 determining locations of S1 and systole (Sys) in a second sequence by using a time duration between peak of R wave (T 1 ) and end of T wave (T 2 ) of a beat from the first sequence; 
 determining locations of S2 and diastole (Dia) in the second sequence by using a the time duration between an end of T wave of a beat and peak of R wave of a next beat from the first sequence; and 
 learning the boundary between the S1 and systole, and the S2 and diastole from a training set. 
 
     
     
       11. The method of  claim 6 , wherein the model based segmentation includes:
 determining fiducial points in the second sequence using Hidden Markov based model (HMM); and 
 dividing T 1  and T 2  into heart phases of S1 and systole, and S2 and diastole, respectively; and 
 learning boundaries from a training set. 
 
     
     
       12. The method of  claim 11 , wherein the model based segmentation further includes a subset of the heart phases. 
     
     
       13. A method of screening of structural heart disease using a wearable sensor device measuring one or more leads of electrocardiogram, phonocardiogram, and accelerometer signals at chest skin surface, the method comprising:
 measuring, by at least one sensor, electrocardiogram (ECG), phonocardiogram (PCG), and accelerometer (ACC) signals on a patient's skin surface and sending the ECG, PCG, and ACC signals to a processor; 
 executing, by the processor, an application stored in a memory to: 
 divide the measured signals into one or more sequences based on a measure of body acceleration; 
 screen decisions on the one or more sequences of the ECG and PCG derived features; 
 determine sequences of aggregate screening decisions; 
 combine the aggregate screening decisions to screen for structural heart disease; and 
 output an indication of a presence of the screened structural heart disease to a display; 
 wherein the screening decisions on one or more sequences of electrocardiogram and phonocardiogram derived features includes feeding each sequence individually into a sequence screening engine, wherein the sequence screening engine relies on two categories of features, including segmentation specific features and sequence specific features to screen the sequence; 
 wherein the screening decisions on one or more sequences of electrocardiogram and phonocardiogram derived features further includes employing independently single channels of segmentation including physiological segmentation and model based segmentation to determine constituent heart stages; and 
 wherein a weighted sum of single channel detections of the physiological and model based segmentation is compared to a threshold to determine a final position of the segments. 
 
     
     
       14. The method of  claim 13 , wherein features are extracted based on at least one of the output of segmentation or from the second sequence. 
     
     
       15. The method of  claim 14 , wherein classification is performed for the segmentation specific features and sequence specific features independently using Classifier A and Classifier B, respectively,
 wherein the Classifier A and the Classifier B includes machine learning algorithms including at least one of: logistic regression, support vector machines, artificial neural networks, or gradient boosting. 
 
     
     
       16. The method of  claim 15 , wherein the output of the classifiers A and B are combined at a final sequence detector, based on a linear or non-linear rule to determine a decision D j .